mes6@njit.edu

Disclaimer : This website is going to be used for Academic Research Purposes.

Bayesian Network

A Bayesian network is a graphical representation of a probabilistic model that describes how the variables in a given system are related. It uses nodes to represent variables and directed edges to represent the statistical relationships between them. This type of model is commonly used in machine learning and data mining applications, as it provides an effective way to model complex systems with many interacting components.

### Bayesian Networks and Conditional Probability

Bayesian networks are based on the concept of conditional probability, which states that the probability of an event occurring depends on other events or conditions. For example, if we know that A influences B and B influences C, then A also influences C. In a Bayesian network, these relationships are represented by directed edges connecting the nodes representing the variables. The strength of each edge reflects its influence on the other node: if two nodes have no edge connecting them, then there is no connection between them; whereas if two nodes have a strong edge between them, then their relationship is stronger than one with a weaker edge. The strength of each edge can be calculated using

Bayes’ theorem, which allows us to calculate the conditional probability of one event given another. Bayesian networks can also be used to answer “what-if” questions by perturbing certain parts of the graph and seeing how this affects the rest of the structure. This helps us gain insight into how different factors interact with each other when certain events occur. For example, if we want to know what would happen if we increased or decreased certain parameters in our system, we can use a Bayesian network to simulate these changes and see how they affect our predictions?